{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8065700531005859, "min": 0.8065700531005859, "max": 2.8704113960266113, "count": 25 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7710.0029296875, "min": 7710.0029296875, "max": 29395.8828125, "count": 25 }, "SnowballTarget.Step.mean": { "value": 249944.0, "min": 9952.0, "max": 249944.0, "count": 25 }, "SnowballTarget.Step.sum": { "value": 249944.0, "min": 9952.0, "max": 249944.0, "count": 25 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.348101615905762, "min": 0.3362118899822235, "max": 13.348101615905762, "count": 25 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2589.53173828125, "min": 65.22510528564453, "max": 2726.5498046875, "count": 25 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 25 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06633483445615389, "min": 0.06111458239511373, "max": 0.07489889763839493, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26533933782461555, "min": 0.2462873867377365, "max": 0.3603157927213675, "count": 25 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19483567244720223, "min": 0.11888761428132305, "max": 0.26933202609127643, "count": 25 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7793426897888089, "min": 0.4755504571252922, "max": 1.346660130456382, "count": 25 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 5.7456980848e-06, "min": 5.7456980848e-06, "max": 0.0002935056021648, "count": 25 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 2.29827923392e-05, "min": 2.29827923392e-05, "max": 0.0014081280306239997, "count": 25 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10191520000000001, "min": 0.10191520000000001, "max": 0.19783520000000002, "count": 25 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.40766080000000005, "min": 0.40766080000000005, "max": 0.9693760000000002, "count": 25 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00010556848000000002, "min": 0.00010556848000000002, "max": 0.004891976480000001, "count": 25 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0004222739200000001, "min": 0.0004222739200000001, "max": 0.023471862399999998, "count": 25 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.318181818181817, "min": 3.3181818181818183, "max": 26.318181818181817, "count": 25 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1158.0, "min": 146.0, "max": 1444.0, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.318181818181817, "min": 3.3181818181818183, "max": 26.318181818181817, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1158.0, "min": 146.0, "max": 1444.0, "count": 25 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1681233624", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1681234232" }, "total": 607.8113277790001, "count": 1, "self": 0.7937804979999328, "children": { "run_training.setup": { "total": 0.11595023800003901, "count": 1, "self": 0.11595023800003901 }, "TrainerController.start_learning": { "total": 606.901597043, "count": 1, "self": 0.7154223130060018, "children": { "TrainerController._reset_env": { "total": 3.893531178000046, "count": 1, "self": 3.893531178000046 }, "TrainerController.advance": { "total": 602.039244233994, "count": 22748, "self": 0.38927751699566215, "children": { "env_step": { "total": 601.6499667169984, "count": 22748, "self": 442.75130237400606, "children": { "SubprocessEnvManager._take_step": { "total": 158.544143622996, "count": 22748, "self": 2.3134919400023364, "children": { "TorchPolicy.evaluate": { "total": 156.23065168299365, "count": 22748, "self": 156.23065168299365 } } }, "workers": { "total": 0.35452071999634427, "count": 22748, "self": 0.0, "children": { "worker_root": { "total": 604.8470533070009, "count": 22748, "is_parallel": true, "self": 286.0784393640048, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005531939999968927, "count": 1, "is_parallel": true, "self": 0.004054904999975406, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014770349999935206, "count": 10, "is_parallel": true, "self": 0.0014770349999935206 } } }, "UnityEnvironment.step": { "total": 0.035547115999975176, "count": 1, "is_parallel": true, "self": 0.0005747949999204138, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004363599999805956, "count": 1, "is_parallel": true, "self": 0.0004363599999805956 }, "communicator.exchange": { "total": 0.032570224000039616, "count": 1, "is_parallel": true, "self": 0.032570224000039616 }, "steps_from_proto": { "total": 0.001965737000034551, "count": 1, "is_parallel": true, "self": 0.0003962009999440852, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015695360000904657, "count": 10, "is_parallel": true, "self": 0.0015695360000904657 } } } } } } }, "UnityEnvironment.step": { "total": 318.7686139429961, "count": 22747, "is_parallel": true, "self": 12.742700046988489, "children": { "UnityEnvironment._generate_step_input": { "total": 7.073926652008936, "count": 22747, "is_parallel": true, "self": 7.073926652008936 }, "communicator.exchange": { "total": 257.0185074850065, "count": 22747, "is_parallel": true, "self": 257.0185074850065 }, "steps_from_proto": { "total": 41.93347975899218, "count": 22747, "is_parallel": true, "self": 8.389928427981317, "children": { "_process_rank_one_or_two_observation": { "total": 33.54355133101086, "count": 227470, "is_parallel": true, "self": 33.54355133101086 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016418699999576347, "count": 1, "self": 0.00016418699999576347, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 597.1641336049599, "count": 551742, "is_parallel": true, "self": 13.815927784912446, "children": { "process_trajectory": { "total": 328.99025636604773, "count": 551742, "is_parallel": true, "self": 326.96288632704784, "children": { "RLTrainer._checkpoint": { "total": 2.0273700389998908, "count": 5, "is_parallel": true, "self": 2.0273700389998908 } } }, "_update_policy": { "total": 254.35794945399977, "count": 113, "is_parallel": true, "self": 95.87687677800176, "children": { "TorchPPOOptimizer.update": { "total": 158.481072675998, "count": 5757, "is_parallel": true, "self": 158.481072675998 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2532351309999967, "count": 1, "self": 0.001713901000016449, "children": { "RLTrainer._checkpoint": { "total": 0.2515212299999803, "count": 1, "self": 0.2515212299999803 } } } } } } }